softmaxLayer

Softmax layer

expand all in page

Description

A softmax layer applies a softmax function to the input.

Creation

Syntax

layer = softmaxLayer

layer = softmaxLayer('Name',Name)

Description

layer= softmaxLayercreates a softmax layer.

example

layer= softmaxLayer('Name',Name)creates a softmax layer and sets the optionalNameproperty using a name-value pair. For example,softmaxLayer('Name','sm1')creates a softmax layer with the name'sm1'. Enclose the property name in single quotes.

Properties

expand all

`Name`—Layer name
`''`(default) |character vector|string scalar

Layer name, specified as a character vector or a string scalar. ForLayerarray input, thetrainNetwork,assembleNetwork,layerGraph, anddlnetworkfunctions automatically assign names to layers with name''.

Data Types:char|string

`NumInputs`—Number of inputs
`1`(default)

This property is read-only.

Number of inputs of the layer. This layer accepts a single input only.

Data Types:double

`InputNames`—Input names
`{'in'}`(default)

This property is read-only.

Input names of the layer. This layer accepts a single input only.

Data Types:cell

`NumOutputs`—Number of outputs
`1`(default)

This property is read-only.

Number of outputs of the layer. This layer has a single output only.

Data Types:double

`OutputNames`—Output names
`{'out'}`(default)

This property is read-only.

Output names of the layer. This layer has a single output only.

Data Types:cell

Examples

collapse all

Create Softmax Layer

Open Live Script

Create a softmax layer with the name 'sm1'.

layer = softmaxLayer('Name','sm1')

layer = SoftmaxLayer with properties: Name: 'sm1'

Include a softmax layer in aLayerarray.

layers = [...imageInputLayer([28 28 1]) convolution2dLayer(5,20) reluLayer maxPooling2dLayer(2,'Stride',2) fullyConnectedLayer(10) softmaxLayer classificationLayer]

层x1 = 7层阵列层:1”的形象nput 28x28x1 images with 'zerocenter' normalization 2 '' Convolution 20 5x5 convolutions with stride [1 1] and padding [0 0 0 0] 3 '' ReLU ReLU 4 '' Max Pooling 2x2 max pooling with stride [2 2] and padding [0 0 0 0] 5 '' Fully Connected 10 fully connected layer 6 '' Softmax softmax 7 '' Classification Output crossentropyex

More About

expand all

Softmax Layer

A softmax layer applies a softmax function to the input.

For classification problems, a softmax layer and then a classification layer usually follow the final fully connected layer.

The output unit activation function is the softmax function:

$y_{r} (x) = \frac{\exp (a_{r} (x))}{\sum_{j = 1}^{k} \exp (a_{j} (x))},$

where $0 \leq y_{r} \leq 1$ and $\sum_{j = 1}^{k} y_{j} = 1$ .

The softmax function is the output unit activation function after the last fully connected layer for multi-class classification problems:

$P (c_{r} | x, θ) = \frac{P (x, θ | c_{r}) P (c_{r})}{\sum_{j = 1}^{k} P (x, θ | c_{j}) P (c_{j})} = \frac{\exp (a_{r} (x, θ))}{\sum_{j = 1}^{k} \exp (a_{j} (x, θ))},$

where $0 \leq P (c_{r} | x, θ) \leq 1$ and $\sum_{j = 1}^{k} P (c_{j} | x, θ) = 1$ . Moreover, $a_{r} = \ln (P (x, θ | c_{r}) P (c_{r}))$ , $P (x, θ | c_{r})$ is the conditional probability of the sample given classr, and $P (c_{r})$ is the class prior probability.

The softmax function is also known as thenormalized exponentialand can be considered the multi-class generalization of the logistic sigmoid function[1].

References

[1] Bishop, C. M.Pattern Recognition and Machine Learning. Springer, New York, NY, 2006.

softmaxLayer

Description

Creation

Syntax

Description

Properties

`Name`—Layer name
`''`(default) |character vector|string scalar

`NumInputs`—Number of inputs
`1`(default)

`InputNames`—Input names
`{'in'}`(default)

`NumOutputs`—Number of outputs
`1`(default)

`OutputNames`—Output names
`{'out'}`(default)

Examples

Create Softmax Layer

More About

Softmax Layer

References

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

GPU Code Generation
Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

Version History

See Also

Topics

softmaxLayer

Description

Creation

Syntax

Description

Properties

Name—Layer name''(default) |character vector|string scalar

NumInputs—Number of inputs1(default)

InputNames—Input names{'in'}(default)

NumOutputs—Number of outputs1(default)

OutputNames—Output names{'out'}(default)

Examples

Create Softmax Layer

More About

Softmax Layer

References

Extended Capabilities

C/C++ Code GenerationGenerate C and C++ code using MATLAB® Coder™.

GPU Code GenerationGenerate CUDA® code for NVIDIA® GPUs using GPU Coder™.

Version History

See Also

Topics

`Name`—Layer name
`''`(default) |character vector|string scalar

`NumInputs`—Number of inputs
`1`(default)

`InputNames`—Input names
`{'in'}`(default)

`NumOutputs`—Number of outputs
`1`(default)

`OutputNames`—Output names
`{'out'}`(default)

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

GPU Code Generation
Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.